scholarly journals Blood glucose prediction using multi-objective grammatical evolution: analysis of the “agnostic” and “what-if” scenarios

2021 ◽  
Author(s):  
Sergio Contador ◽  
J. Manuel Colmenar ◽  
Oscar Garnica ◽  
J. Manuel Velasco ◽  
J. Ignacio Hidalgo
Keyword(s):  
Ad Hoc ◽  
Fitness Function ◽  
Grammatical Evolution ◽  
Diabetic Patients ◽  
Regression Problem ◽  
Multi Objective ◽  
Grid Analysis ◽  
Future Events ◽  
Clarke Error Grid ◽  
Error Grid

AbstractIn this paper we investigate the benefits of applying a multi-objective approach for solving a symbolic regression problem by means of Grammatical Evolution. In particular, we extend previous work, obtaining mathematical expressions to model glucose levels in the blood of diabetic patients. Here we use a multi-objective Grammatical Evolution approach based on the NSGA-II algorithm, considering the root-mean-square error and an ad-hoc fitness function as objectives. This ad-hoc function is based on the Clarke Error Grid analysis, which is useful for showing the potential danger of mispredictions in diabetic patients. In this work, we use two datasets to analyse two different scenarios: What-if and Agnostic, the most common in daily clinical practice. In the What-if scenario, where future events are evaluated, results show that the multi-objective approach improves previous results in terms of Clarke Error Grid analysis by reducing the number of dangerous mispredictions. In the Agnostic situation, with no available information about future events, results suggest that we can obtain good predictions with only information from the previous hour for both Grammatical Evolution and Multi-Objective Grammatical Evolution.

scholarly journals Accuracy of Flash Glucose Monitoring During Postprandial Rest and Different Walking Conditions in Overweight or Obese Young Adults

2021 ◽  
Vol 12 ◽  
Author(s):  
Xiaoyuan Zhang ◽  
Fenghua Sun ◽  
Waris Wongpipit ◽  
Wendy Y. J. Huang ◽  
Stephen H. S. Wong
Keyword(s):  
Young Adults ◽  
Glucose Monitoring ◽  
Postprandial Glucose ◽  
Relative Difference ◽  
Flash Glucose Monitoring ◽  
Grid Analysis ◽  
Crossover Studies ◽  
Freestyle Libre ◽  
Clarke Error Grid ◽  
Error Grid

Aims: To investigate the accuracy of FreeStyle LibreTM flash glucose monitoring (FGM) relevant to plasma glucose (PG) measurements during postprandial rest and different walking conditions in overweight/obese young adults.Methods: Data of 40 overweight/obese participants from two randomized crossover studies were pooled into four trials: (1) sitting (SIT, n = 40); (2) walking continuously for 30 min initiated 20 min before individual postprandial glucose peak (PPGP) (20iP + CONT, n = 40); (3) walking continuously for 30 min initiated at PPGP (iP + CONT, n = 20); and (4) accumulated walking for 30 min initiated 20 min before PPGP (20iP + ACCU, n = 20). Paired FGM and PG were measured 4 h following breakfast.Results: The overall mean absolute relative difference (MARD) between PG and FGM readings was 16.4 ± 8.6% for SIT, 16.2 ± 4.7% for 20iP + CONT, 16.7 ± 12.2% for iP + CONT, and 19.1 ± 6.8% for 20iP + ACCU. The Bland–Altman analysis showed a bias of −1.03 mmol⋅L–1 in SIT, −0.89 mmol⋅L–1 in 20iP + CONT, −0.82 mmol⋅L–1 in iP + CONT, and −1.23 mmol⋅L–1 in 20iP + ACCU. The Clarke error grid analysis showed that 99.6–100% of the values in all trials fell within zones A and B.Conclusion: Although FGM readings underestimated PG, the FGM accuracy was overall clinically acceptable during postprandial rest and walking in overweight/obese young adults.

scholarly journals Newer Portable Glucose Meters—Analytical Improvement Compared with Previous Generation Devices?

1999 ◽  
Vol 45 (10) ◽  
pp. 1821-1825 ◽  
Author(s):  
Raimund Weitgasser ◽  
Brigitta Gappmayer ◽  
Maximilian Pichler
Keyword(s):  
Blood Glucose ◽  
Reference Value ◽  
Comparison Method ◽  
Maximum Deviation ◽  
Diabetic Patients ◽  
Grid Analysis ◽  
Previous Generation ◽  
In Series ◽  
The One ◽  
Error Grid

Abstract Background: Newer glucose meters are easier to use, but direct comparisons with older instruments are lacking. We wished to compare analytical performances of four new and four previous generation meters. Methods: On average, 248 glucose measurements were performed with two of each brand of meter on capillary blood samples from diabetic patients attending our outpatient clinic. Two to three different lots of strips were used. All measurements were performed by one experienced technician, using blood from the same sample for the meters and the comparison method (Beckman Analyzer 2). Results were evaluated by analysis of clinical relevance using the percentage of values within a maximum deviation of 5% from the reference value, by the method of residuals, by error grid analysis, and by the CVs for measurements in series. Results: Altogether, 1987 blood glucose values were obtained with meters compared with the reference values. By error grid analysis, the newer devices gave more accurate results without significant differences within the group (zone A, 98–98.5%). Except for the One Touch II (zone A, 98.5%), the other older devices were less exact (zone A, 87–92.5%), which was also true for all other evaluation procedures. Conclusions: New generation blood glucose meters are not only smaller and more aesthetically appealing but are more accurate compared with previous generation devices except the One Touch II. The performance of the newer meters improved but did not meet the goals of the latest American Diabetes Association recommendations in the hands of an experienced operator.

scholarly journals Continuous Glucose Monitoring in the Intensive Care Unit Following Total Pancreatectomy with Islet Autotransplantation in Children: Establishing Accuracy of the Dexcom G6 Model

2021 ◽  
Vol 10 (9) ◽  
pp. 1893
Author(s):  
Natalie Segev ◽  
Lindsey N. Hornung ◽  
Siobhan E. Tellez ◽  
Joshua D. Courter ◽  
Sarah A. Lawson ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Continuous Glucose Monitoring ◽  
Total Pancreatectomy ◽  
Glucose Monitoring ◽  
Absolute Difference ◽  
Grid Analysis ◽  
Clarke Error Grid ◽  
Islet Autotransplantation ◽  
Error Grid

Hyperglycemia is detrimental to postoperative islet cell survival in patients undergoing total pancreatectomy with islet autotransplantation (TPIAT). This makes continuous glucose monitoring (CGM) a useful management tool. We evaluated the accuracy of the Dexcom G6 CGM in pediatric intensive care unit patients following TPIAT. Twenty-five patients who underwent TPIAT had Dexcom G6 glucose values compared to paired serum glucose values. All paired glucose samples were obtained within 5 minutes of each other during the first seven days post TPIAT. Data were evaluated using mean absolute difference (MAD), mean absolute relative difference (MARD), %20/20, %15/15 accuracy, and Clarke Error Grid analysis. Exclusions included analysis during the CGM “warm-up” period and hydroxyurea administration (known drug interference). A total of 183 time-matched samples were reviewed during postoperative days 2–7. MAD was 14.7 mg/dL and MARD was 13.4%, with values of 15.2%, 14.0%, 12.1%, 11.4%, 13.2% and 14.1% at days 2, 3, 4, 5, 6 and 7, respectively. Dexcom G6 had a %20/20 accuracy of 78%, and a %15/15 accuracy of 64%. Clarke Error Grid analysis showed that 77% of time-matched values were clinically accurate, and 100% were clinically acceptable. The Dexcom G6 CGM may be an accurate tool producing clinically acceptable values to make reliable clinical decisions in the immediate post-TPIAT period.

Sign in / Sign up

Export Citation Format

Share Document